General approach for time series classification is splitting time series to equal size Multivariate time series classification is a high segments using a fixed-length sliding window and extracting value and well-known problem in machine learning handcrafted features from the segments for classification community. Feature extraction is a main step tasks. The features are usually statistical measurements or in classification tasks. Traditional approaches employ features extracted from another domain such Fourier and handcrafted features for classification while Wavelet domain (Jiang & Yin, 2015; Ravi et al., 2017; Lin convolutional neural networks (CNN) are able et al., 2003). In multivariate time series classification, commonly, to extract features automatically. In this paper, information is extracted separately from each variate, we use dilated convolutional neural network for and the features are concatenated for the classification task multivariate time series classification.

Effective understanding of the environment and accurate trajectory prediction of surrounding dynamic obstacles are critical for intelligent systems such as autonomous vehicles and wheeled mobile robotics navigating in complex scenarios to achieve safe and high-quality decision making, motion planning and control. Due to the uncertain nature of the future, it is desired to make inference from a probability perspective instead of deterministic prediction. In this paper, we propose a conditional generative neural system (CGNS) for probabilistic trajectory prediction to approximate the data distribution, with which realistic, feasible and diverse future trajectory hypotheses can be sampled. The system combines the strengths of conditional latent space learning and variational divergence minimization, and leverages both static context and interaction information with soft attention mechanisms. We also propose a regularization method for incorporating soft constraints into deep neural networks with differentiable barrier functions, which can regulate and push the generated samples into the feasible regions. The proposed system is evaluated on several public benchmark datasets for pedestrian trajectory prediction and a roundabout naturalistic driving dataset collected by ourselves. The experiment results demonstrate that our model achieves better performance than various baseline approaches in terms of prediction accuracy.

This paper provides an analysis of the tradeoff between asymptotic bias (suboptimality with unlimited data) and overfitting (additional suboptimality due to limited data) in the context of reinforcement learning with partial observability. Our theoretical analysis formally characterizes that while potentially increasing the asymptotic bias, a smaller state representation decreases the risk of overfitting. This analysis relies on expressing the quality of a state representation by bounding $L_1$ error terms of the associated belief states.  Theoretical results are empirically illustrated when the state representation is a truncated history of observations, both on synthetic POMDPs and on a large-scale POMDP in the context of smartgrids, with real-world data. Finally, similarly to known results in the fully observable setting, we also briefly discuss and empirically illustrate how using function approximators and adapting the discount factor may enhance the tradeoff between asymptotic bias and overfitting in the partially observable context.

This paper aims to learn a compact representation of a video for video face recognition task. We make the following contributions: first, we propose a meta attention-based aggregation scheme which adaptively and fine-grained weighs the feature along each feature dimension among all frames to form a compact and discriminative representation. It makes the best to exploit the valuable or discriminative part of each frame to promote the performance of face recognition, without discarding or despising low quality frames as usual methods do. Second, we build a feature aggregation network comprised of a feature embedding module and a feature aggregation module. The embedding module is a convolutional neural network used to extract a feature vector from a face image, while the aggregation module consists of cascaded two meta attention blocks which adaptively aggregate the feature vectors into a single fixed-length representation. The network can deal with arbitrary number of frames, and is insensitive to frame order. Third, we validate the performance of proposed aggregation scheme. Experiments on publicly available datasets, such as YouTube face dataset and IJB-A dataset, show the effectiveness of our method, and it achieves competitive performances on both the verification and identification protocols.

Cooking is a task that must be performed in a daily basis, and thus it is an activity that many people take for granted. For humans preparing a meal comes naturally, but for robots even preparing a simple sandwich results in an extremely difficult task. In robotics, designing kitchen robots is complicated since cooking relies on a variety of physical interactions that are dependent on different conditions such as changes in the environment, proper execution of sequential instructions, along with motions, and detection of the different states in which cooking-ingredients can be in for their correct grasping and manipulation. In this paper, we focus on the challenge of state recognition and propose a fine tuned convolutional neural network that makes use of transfer learning by reusing the Inception V3 pre-trained model. The model is trained and validated on a cooking dataset consisting of eleven states (e.g. peeled, diced, whole, etc.). The work presented on this paper could provide insight into finding a potential solution to the problem.

For network architecture search (NAS), it is crucial but challenging to simultaneously guarantee both effectiveness and efficiency. Towards achieving this goal, we develop a differentiable NAS solution, where the search space includes arbitrary feed-forward network consisting of the predefined number of connections. Benefiting from a proposed ensemble Gumbel-Softmax estimator, our method optimizes both the architecture of a deep network and its parameters in the same round of backward propagation, yielding an end-to-end mechanism of searching network architectures. Extensive experiments on a variety of popular datasets strongly evidence that our method is capable of discovering high-performance architectures, while guaranteeing the requisite efficiency during searching.

A large body of recent work has investigated the phenomenon of evasion attacks using adversarial examples for deep learning systems, where the addition of norm-bounded perturbations to the test inputs leads to incorrect output classification. Previous work has investigated this phenomenon in closed-world systems where training and test inputs follow a pre-specified distribution. However, real-world implementations of deep learning applications, such as autonomous driving and content classification are likely to operate in the open-world environment. In this paper, we demonstrate the success of open-world evasion attacks, where adversarial examples are generated from out-of-distribution inputs (OOD adversarial examples). In our study, we use 11 state-of-the-art neural network models trained on 3 image datasets of varying complexity. We first demonstrate that state-of-the-art detectors for out-of-distribution data are not robust against OOD adversarial examples. We then consider 5 known defenses for adversarial examples, including state-of-the-art robust training methods, and show that against these defenses, OOD adversarial examples can achieve up to 4$\times$ higher target success rates compared to adversarial examples generated from in-distribution data. We also take a quantitative look at how open-world evasion attacks may affect real-world systems. Finally, we present the first steps towards a robust open-world machine learning system.

Traditional clustering methods often perform clustering with low-level indiscriminative representations and ignore relationships between patterns, resulting in slight achievements in the era of deep learning. To handle this problem, we develop Deep Discriminative Clustering (DDC) that models the clustering task by investigating relationships between patterns with a deep neural network. Technically, a global constraint is introduced to adaptively estimate the relationships, and a local constraint is developed to endow the network with the capability of learning high-level discriminative representations. By iteratively training the network and estimating the relationships in a mini-batch manner, DDC theoretically converges and the trained network enables to generate a group of discriminative representations that can be treated as clustering centers for straightway clustering. Extensive experiments strongly demonstrate that DDC outperforms current methods on eight image, text and audio datasets concurrently.

But innovation in chipmaking has been spurred mostly by the emergence of deep learning, a very powerful way for machines to learn to perform useful tasks. Instead of giving a computer a set of rules to follow, a machine basically programs itself. Training data is fed into a large, simulated artificial neural network, which is then tweaked so that it produces the desired result. With enough training, a deep-learning system can find subtle and abstract patterns in data. The technique is applied to an ever-growing array of practical tasks, from face recognition on smartphones to predicting disease from medical images.

This is an eclectic collection of interesting blog posts, software announcements and data applications from Microsoft and elsewhere that I've noted over the past month or so. TensorFlow Privacy: a Python library for training machine learning models with differential privacy, for use with sensitive data to generate models that don't learn details about specific people. Tensorflow Federated, an open-source library for Federated Learning, enabling many participating clients to train shared ML models while keeping their data local. Open AI has published a paper describing GPT-2, an unsupervised language model that can generate paragraphs of coherent text that could be mistaken for human writing. Only a scaled-down version has been released, for fear of abuse.